微信图-CSDN博客

import requests
from lxml import etree
# User-Agent:Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36

def body():
    url = "https://mp.weixin.qq.com/s/BzDw9nWASnOkmgWcfl6MuA"
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'}
    respones = requests.get(url,headers=header)
    # print(respones)
    respones.encoding = "utf_8"
    html = respones.text
    obj = etree.HTML(html)
    obj_body = obj.xpath('//div[@class="rich_media_content "]//img/@data-src')
    del obj_body[0]
    print(obj_body)
    ret = len(obj_body)
    print(ret)
    obj_titer = obj.xpath('//div[@class="rich_media_content "]//strong//span/text()')
    y = []
    for i in obj_titer:
        res = i.strip('\xa0\xa0☟')
        y.append(res)
    print(y)







    for i,ref in zip(obj_body,y):
        r = requests.get(i)
        with open(r"F:\day08\人民日报\微信图片\%s.gif"%ref,"wb") as f:
            f.write(r.content)

body()

转载于:https://www.cnblogs.com/heluobing/p/10909667.html